Joint estimation of linear and non-linear signal-to-noise ratio based on neural networks
2018 Optical Fiber Communications Conference and Exposition (OFC), 2018•ieeexplore.ieee.org
… Our method is evaluated by simulations obtaining a std error of 0.23 dB for both ASE and
non-linear SNR. … Current research focuses on different definitions of the amplitude noise
covariance to estimate the NLI based on linear regressions [5] or Neural Networks (NN) [6].
Others … We developed and evaluated a novel technique for jointly estimating SNRASE
and SNRNLI with std error of 0.23 dB over a wide range of fibres, ASE-to-NLI ratios, WDM
channels, and distances. The proposed metric is simple, requiring the extraction of basic …
non-linear SNR. … Current research focuses on different definitions of the amplitude noise
covariance to estimate the NLI based on linear regressions [5] or Neural Networks (NN) [6].
Others … We developed and evaluated a novel technique for jointly estimating SNRASE
and SNRNLI with std error of 0.23 dB over a wide range of fibres, ASE-to-NLI ratios, WDM
channels, and distances. The proposed metric is simple, requiring the extraction of basic …
A novel technique estimating ASE and non-linear SNR is presented. Our method is evaluated by simulations obtaining a std error of 0.23 dB for both ASE and non-linear SNR.
ieeexplore.ieee.org